It has been reported that the "National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging," which has been under construction for 3 years, has recently passed the comprehensive performance evaluation of the High-Tech Research and Development Center of the Ministry of Science and Technology. This marks the complete integration of China's medical imaging AI from "laboratory" research to "hospital" clinical application.
Initiated in 2021 as part of the "National Major Science and Technology Project for the Next Generation of Artificial Intelligence," this project is led by Tencent, with the participation of 10 units including the China Academy of Information and Communications Technology, the Shenzhen Institute of Advanced Technology of the Chinese Academy of Sciences, and the Southern Medical University Nanfang Hospital. It focuses on tackling the "bottleneck" issues hindering the development of medical imaging AI in China, including integrating and opening up common technologies, sharing open-source code, and constructing basic medical data resources.
Architecture of the National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging. Image provided by the interviewee.
As early as 2017, the Ministry of Science and Technology issued the "Implementation Plan for Major Science and Technology Projects of the Next Generation Artificial Intelligence," relying on Tencent to build the "National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging." Currently, leveraging Tencent Cloud technology, the platform has established a SaaS service platform supporting multimodal and multi-disease types, enabling the entire process of medical AI research and development, including storage, statistics, annotation, artificial intelligence model training, and validation of medical imaging data.
The platform realizes efficient utilization of medical imaging AI through cloud-based open-source technology, achieving "ready-to-use" functionality with internet access. It has served over 4,000 research units and users, with over 70,000 cases of medical imaging data annotated. Tencent has also opened six self-developed medical imaging AI models to support the construction of the National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging. Currently, the platform has integrated 41 algorithm model research projects and applied the aforementioned open models.
Furthermore, based on the requirements of multicenter, multimodal, and multi-disease types, the National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging has constructed a standardized open and shared medical imaging database. The dataset comprises over 12,000 cases, covering 13 diseases including lymphoma, lung cancer, renal tumors, Crohn's disease, meningioma, and cervical cancer. Through open access, this imaging database will further assist researchers in training and validating AI algorithms.
The platform can annotate medical images of 10 diseases, such as meningioma MRI images, provided by respondents.
Over the past three years, units involved in the construction of the "National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging" have been dedicated to transforming medical imaging AI technology into industrial achievements, benefiting the public through extensive applications. The platform has successively incubated various innovative products, such as Tencent's Miiying pneumonia CT image-assisted triage and evaluation software, chronic glaucoma-like optic nerve disease fundus image-assisted diagnostic software, colon polyp electronic endoscopy image-assisted detection software, as well as pathological cloud and image cloud, all of which have obtained medical device certificates.
In addition, Haina Yixin's AI hierarchical diagnosis and treatment cloud platform has been connected to 8 secondary and tertiary hospitals, as well as 28 community health service centers, and has expanded overseas. Yiduyun's remote monitoring platform has been launched in more than 10 important clinical trial hospitals in China, supporting thousands of projects cumulatively. In terms of building a new model of industry-university-research cooperation, the "National Next-Generation Artificial Intelligence Open Innovation Platform for Medical Imaging" has established a sharing mechanism, further promoting exchanges and cooperation between universities, research institutes, and enterprises.
To further strengthen talent training, Tencent, along with multiple institutions, has initiated the "Public Health Talent Enhancement Project," training a number of core experts and young professional backbones for national and local disease control agencies.
